Radeon RX 6750 GRE 10 GB

The Radeon RX 6750 GRE 10 GB is an Amd GPU built on the RDNA 2.0 architecture, released 2023-10-17. For running AI locally, the numbers that matter are its 10 GB of GDDR6 and 320 GB/s of memory bandwidth. VRAM decides which models fit at all; bandwidth sets how fast they generate text.

What you can run on 10 GB

At Q4_K_M quantization (the usual local default), 10 GB holds models up to roughly 15B parameters, leaving headroom for context. On this card you can run, among others:

• Qwen2.5-14B-Instruct - 14.8B parameters
• Qwen2.5-Coder-14B-Instruct - 14.8B parameters
• Phi-4 - 14B parameters
• Qwen3 14B - 14B parameters
• Wan2.1 T2V 14B - 14B parameters

Larger models need a higher-VRAM card, a second GPU, or CPU offload (which is much slower). Check any specific model with the VRAM calculator, or see the full picture on what can I run.

Local LLM speed (LLaMA 3, llama.cpp)

Single-stream token-generation throughput - estimated from memory bandwidth:

Model (quant)	Speed on Radeon RX 6750 GRE 10 GB
Llama 3 8B (Q4_K_M)	37.4 tok/s
Llama 3 8B (F16)	✗ won't fit
Llama 3 70B (Q4_K_M)	✗ won't fit

Because decode is memory-bandwidth bound, the 320 GB/s figure is the best single predictor of chat speed on this card. Estimates are calibrated against measured RTX-40-series cards and are typically within ~15%.

Memory and power

• VRAM: 10 GB GDDR6 (160-bit bus)
• Bandwidth: 320 GB/s
• TDP: 170 W - a 450 W+ power supply is recommended
• Process: 7 nm
• Interface: PCIe 4.0 x16

Quantization and context

Quantization trades a little quality for a lot of VRAM. On 10 GB you can fit roughly a 15B model at Q4_K_M, about a 8B model at the higher-quality Q8, or a smaller model at full FP16. Longer context windows also consume VRAM (the KV cache grows with context length), so leave a few GB of headroom if you plan to use large prompts or many concurrent requests. For most chat and coding use, Q4_K_M on this card is the sweet spot between speed, quality, and the 10 GB budget.

How it compares

Similar cards for local AI, by VRAM and 8B-Q4 speed:

GPU	VRAM	Bandwidth	Llama 3 8B Q4
Radeon RX 6750 GRE 10 GB	10 GB	320 GB/s	37.4 tok/s
Intel Arc B570	10 GB	360 GB/s	42.1 tok/s
NVIDIA RTX 3080 10GB	10 GB	760 GB/s	106.4 tok/s
NVIDIA RTX 2080 Ti	11 GB	616 GB/s	72.1 tok/s

Bottom line

The Radeon RX 6750 GRE 10 GB is best for entry-level, budget-llm. With under 12 GB, stick to small quantized models (up to ~7B). If you need more, compare with Intel Arc B570 and NVIDIA RTX 3080 10GB.

Sources

• Specifications: RightNow GPU Database (TechPowerUp data)
• Benchmarks: GPU-Benchmarks-on-LLM-Inference (basis for the bandwidth estimate)

Specs and benchmarks last checked 2026-06-08. Verify current pricing before buying.